Commit
•
fcb4856
1
Parent(s):
c989dcb
Model save
Browse files- README.md +5 -5
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +9 -9
- eval_results.json +5 -5
- runs/Dec15_05-26-11_s4311/events.out.tfevents.1702618051.s4311.1026368.0 +3 -0
- runs/Dec15_05-26-11_s4311/events.out.tfevents.1702624031.s4311.1026368.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +53 -35
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 1.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
-
| 1.
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 1.
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.2383
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| 1.3801 | 0.35 | 4 | 1.3500 |
|
53 |
+
| 1.3615 | 1.32 | 8 | 1.3000 |
|
54 |
+
| 1.3064 | 2.3 | 12 | 1.2652 |
|
55 |
+
| 1.2626 | 3.37 | 17 | 1.2383 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -16,10 +16,10 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"v_proj",
|
20 |
-
"q_proj",
|
21 |
"k_proj",
|
22 |
-
"o_proj"
|
|
|
|
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
25 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
|
|
19 |
"k_proj",
|
20 |
+
"o_proj",
|
21 |
+
"q_proj",
|
22 |
+
"v_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
25 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218138576
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:733d047eede5712a63861b5f2821d0f11d45ce7cc9eef9931d98de25e00c1e80
|
3 |
size 218138576
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
-
"epoch": 3.
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 294,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"train_loss": 1.
|
9 |
-
"train_runtime":
|
10 |
"train_samples": 5895,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 3.37,
|
3 |
+
"eval_loss": 1.2383112907409668,
|
4 |
+
"eval_runtime": 22.4776,
|
5 |
"eval_samples": 294,
|
6 |
+
"eval_samples_per_second": 13.08,
|
7 |
+
"eval_steps_per_second": 1.646,
|
8 |
+
"train_loss": 1.30483017949497,
|
9 |
+
"train_runtime": 5957.4264,
|
10 |
"train_samples": 5895,
|
11 |
+
"train_samples_per_second": 3.958,
|
12 |
+
"train_steps_per_second": 0.007
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 3.
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 294,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 3.37,
|
3 |
+
"eval_loss": 1.2383112907409668,
|
4 |
+
"eval_runtime": 22.4776,
|
5 |
"eval_samples": 294,
|
6 |
+
"eval_samples_per_second": 13.08,
|
7 |
+
"eval_steps_per_second": 1.646
|
8 |
}
|
runs/Dec15_05-26-11_s4311/events.out.tfevents.1702618051.s4311.1026368.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17f33fcbcaf4a4ec5a6538ae3e5c63fe8a143b8ed099bf9b8607c390736e5aa8
|
3 |
+
size 6281
|
runs/Dec15_05-26-11_s4311/events.out.tfevents.1702624031.s4311.1026368.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fa0b59f1d02d339bea48d497f4ff5acc85dc6a989e62ed82b0b704ead91ab41
|
3 |
+
size 354
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 3.
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 5895,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 3.37,
|
3 |
+
"train_loss": 1.30483017949497,
|
4 |
+
"train_runtime": 5957.4264,
|
5 |
"train_samples": 5895,
|
6 |
+
"train_samples_per_second": 3.958,
|
7 |
+
"train_steps_per_second": 0.007
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 3.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -11,56 +11,74 @@
|
|
11 |
{
|
12 |
"epoch": 0.09,
|
13 |
"learning_rate": 1.9974521146102535e-05,
|
14 |
-
"loss": 1.
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0.
|
19 |
-
"eval_loss": 1.
|
20 |
-
"eval_runtime":
|
21 |
-
"eval_samples_per_second":
|
22 |
-
"eval_steps_per_second":
|
23 |
-
"step":
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 1.
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"eval_steps_per_second": 5.832,
|
31 |
-
"step": 2
|
32 |
},
|
33 |
{
|
34 |
-
"epoch":
|
35 |
-
"eval_loss": 1.
|
36 |
-
"eval_runtime":
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second":
|
39 |
-
"step":
|
40 |
},
|
41 |
{
|
42 |
-
"epoch":
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
|
47 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
},
|
49 |
{
|
50 |
-
"epoch": 3.
|
51 |
-
"step":
|
52 |
-
"total_flos":
|
53 |
-
"train_loss": 1.
|
54 |
-
"train_runtime":
|
55 |
-
"train_samples_per_second":
|
56 |
-
"train_steps_per_second": 0.
|
57 |
}
|
58 |
],
|
59 |
"logging_steps": 5,
|
60 |
"max_steps": 44,
|
61 |
"num_train_epochs": 4,
|
62 |
"save_steps": 500,
|
63 |
-
"total_flos":
|
64 |
"trial_name": null,
|
65 |
"trial_params": null
|
66 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.3670284938941655,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 17,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
11 |
{
|
12 |
"epoch": 0.09,
|
13 |
"learning_rate": 1.9974521146102535e-05,
|
14 |
+
"loss": 1.3801,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.35,
|
19 |
+
"eval_loss": 1.3500080108642578,
|
20 |
+
"eval_runtime": 22.5154,
|
21 |
+
"eval_samples_per_second": 13.058,
|
22 |
+
"eval_steps_per_second": 1.643,
|
23 |
+
"step": 4
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 1.06,
|
27 |
+
"learning_rate": 1.936949724999762e-05,
|
28 |
+
"loss": 1.3615,
|
29 |
+
"step": 5
|
|
|
|
|
30 |
},
|
31 |
{
|
32 |
+
"epoch": 1.32,
|
33 |
+
"eval_loss": 1.2999709844589233,
|
34 |
+
"eval_runtime": 22.4738,
|
35 |
+
"eval_samples_per_second": 13.082,
|
36 |
+
"eval_steps_per_second": 1.646,
|
37 |
+
"step": 8
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 2.13,
|
41 |
+
"learning_rate": 1.7557495743542586e-05,
|
42 |
+
"loss": 1.3064,
|
43 |
+
"step": 10
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 2.3,
|
47 |
+
"eval_loss": 1.265210747718811,
|
48 |
+
"eval_runtime": 22.4153,
|
49 |
+
"eval_samples_per_second": 13.116,
|
50 |
+
"eval_steps_per_second": 1.651,
|
51 |
+
"step": 12
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 3.19,
|
55 |
+
"learning_rate": 1.479248986720057e-05,
|
56 |
+
"loss": 1.2626,
|
57 |
+
"step": 15
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 3.37,
|
61 |
+
"eval_loss": 1.2383277416229248,
|
62 |
+
"eval_runtime": 22.5157,
|
63 |
+
"eval_samples_per_second": 13.058,
|
64 |
+
"eval_steps_per_second": 1.643,
|
65 |
+
"step": 17
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 3.37,
|
69 |
+
"step": 17,
|
70 |
+
"total_flos": 7.670550714342441e+17,
|
71 |
+
"train_loss": 1.30483017949497,
|
72 |
+
"train_runtime": 5957.4264,
|
73 |
+
"train_samples_per_second": 3.958,
|
74 |
+
"train_steps_per_second": 0.007
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 5,
|
78 |
"max_steps": 44,
|
79 |
"num_train_epochs": 4,
|
80 |
"save_steps": 500,
|
81 |
+
"total_flos": 7.670550714342441e+17,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f1941f27569a238b088377cad71a086145d5d62cbf0cd926c9aae68936ed966
|
3 |
size 4664
|